CN108628282A - Analyte sensors data are to detect the unsupervised algorithm of data-driven of abnormal valve operation - Google Patents
Analyte sensors data are to detect the unsupervised algorithm of data-driven of abnormal valve operation Download PDFInfo
- Publication number
- CN108628282A CN108628282A CN201810207808.5A CN201810207808A CN108628282A CN 108628282 A CN108628282 A CN 108628282A CN 201810207808 A CN201810207808 A CN 201810207808A CN 108628282 A CN108628282 A CN 108628282A
- Authority
- CN
- China
- Prior art keywords
- valve
- shut
- sensor
- mmsg
- parameter
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/109—Time management, e.g. calendars, reminders, meetings or time accounting
- G06Q10/1093—Calendar-based scheduling for persons or groups
- G06Q10/1097—Task assignment
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
- G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
- G05B23/0218—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults
- G05B23/0221—Preprocessing measurements, e.g. data collection rate adjustment; Standardization of measurements; Time series or signal analysis, e.g. frequency analysis or wavelets; Trustworthiness of measurements; Indexes therefor; Measurements using easily measured parameters to estimate parameters difficult to measure; Virtual sensor creation; De-noising; Sensor fusion; Unconventional preprocessing inherently present in specific fault detection methods like PCA-based methods
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F01—MACHINES OR ENGINES IN GENERAL; ENGINE PLANTS IN GENERAL; STEAM ENGINES
- F01D—NON-POSITIVE DISPLACEMENT MACHINES OR ENGINES, e.g. STEAM TURBINES
- F01D21/00—Shutting-down of machines or engines, e.g. in emergency; Regulating, controlling, or safety means not otherwise provided for
- F01D21/003—Arrangements for testing or measuring
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F16—ENGINEERING ELEMENTS AND UNITS; GENERAL MEASURES FOR PRODUCING AND MAINTAINING EFFECTIVE FUNCTIONING OF MACHINES OR INSTALLATIONS; THERMAL INSULATION IN GENERAL
- F16K—VALVES; TAPS; COCKS; ACTUATING-FLOATS; DEVICES FOR VENTING OR AERATING
- F16K37/00—Special means in or on valves or other cut-off apparatus for indicating or recording operation thereof, or for enabling an alarm to be given
- F16K37/0075—For recording or indicating the functioning of a valve in combination with test equipment
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F16—ENGINEERING ELEMENTS AND UNITS; GENERAL MEASURES FOR PRODUCING AND MAINTAINING EFFECTIVE FUNCTIONING OF MACHINES OR INSTALLATIONS; THERMAL INSULATION IN GENERAL
- F16K—VALVES; TAPS; COCKS; ACTUATING-FLOATS; DEVICES FOR VENTING OR AERATING
- F16K37/00—Special means in or on valves or other cut-off apparatus for indicating or recording operation thereof, or for enabling an alarm to be given
- F16K37/0075—For recording or indicating the functioning of a valve in combination with test equipment
- F16K37/0083—For recording or indicating the functioning of a valve in combination with test equipment by measuring valve parameters
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
- G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
- G05B23/0218—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults
- G05B23/0224—Process history based detection method, e.g. whereby history implies the availability of large amounts of data
- G05B23/0227—Qualitative history assessment, whereby the type of data acted upon, e.g. waveforms, images or patterns, is not relevant, e.g. rule based assessment; if-then decisions
- G05B23/0235—Qualitative history assessment, whereby the type of data acted upon, e.g. waveforms, images or patterns, is not relevant, e.g. rule based assessment; if-then decisions based on a comparison with predetermined threshold or range, e.g. "classical methods", carried out during normal operation; threshold adaptation or choice; when or how to compare with the threshold
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
- G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
- G05B23/0218—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults
- G05B23/0224—Process history based detection method, e.g. whereby history implies the availability of large amounts of data
- G05B23/024—Quantitative history assessment, e.g. mathematical relationships between available data; Functions therefor; Principal component analysis [PCA]; Partial least square [PLS]; Statistical classifiers, e.g. Bayesian networks, linear regression or correlation analysis; Neural networks
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
- G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
- G05B23/0259—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterized by the response to fault detection
- G05B23/0283—Predictive maintenance, e.g. involving the monitoring of a system and, based on the monitoring results, taking decisions on the maintenance schedule of the monitored system; Estimating remaining useful life [RUL]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B64—AIRCRAFT; AVIATION; COSMONAUTICS
- B64F—GROUND OR AIRCRAFT-CARRIER-DECK INSTALLATIONS SPECIALLY ADAPTED FOR USE IN CONNECTION WITH AIRCRAFT; DESIGNING, MANUFACTURING, ASSEMBLING, CLEANING, MAINTAINING OR REPAIRING AIRCRAFT, NOT OTHERWISE PROVIDED FOR; HANDLING, TRANSPORTING, TESTING OR INSPECTING AIRCRAFT COMPONENTS, NOT OTHERWISE PROVIDED FOR
- B64F5/00—Designing, manufacturing, assembling, cleaning, maintaining or repairing aircraft, not otherwise provided for; Handling, transporting, testing or inspecting aircraft components, not otherwise provided for
- B64F5/60—Testing or inspecting aircraft components or systems
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F01—MACHINES OR ENGINES IN GENERAL; ENGINE PLANTS IN GENERAL; STEAM ENGINES
- F01D—NON-POSITIVE DISPLACEMENT MACHINES OR ENGINES, e.g. STEAM TURBINES
- F01D21/00—Shutting-down of machines or engines, e.g. in emergency; Regulating, controlling, or safety means not otherwise provided for
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F16—ENGINEERING ELEMENTS AND UNITS; GENERAL MEASURES FOR PRODUCING AND MAINTAINING EFFECTIVE FUNCTIONING OF MACHINES OR INSTALLATIONS; THERMAL INSULATION IN GENERAL
- F16K—VALVES; TAPS; COCKS; ACTUATING-FLOATS; DEVICES FOR VENTING OR AERATING
- F16K37/00—Special means in or on valves or other cut-off apparatus for indicating or recording operation thereof, or for enabling an alarm to be given
- F16K37/0075—For recording or indicating the functioning of a valve in combination with test equipment
- F16K37/0091—For recording or indicating the functioning of a valve in combination with test equipment by measuring fluid parameters
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M15/00—Testing of engines
- G01M15/14—Testing gas-turbine engines or jet-propulsion engines
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M99/00—Subject matter not provided for in other groups of this subclass
- G01M99/005—Testing of complete machines, e.g. washing-machines or mobile phones
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
- G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
- G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
- G05B23/0218—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
- G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
- G05B23/0218—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults
- G05B23/0243—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults model based detection method, e.g. first-principles knowledge model
- G05B23/0254—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults model based detection method, e.g. first-principles knowledge model based on a quantitative model, e.g. mathematical relationships between inputs and outputs; functions: observer, Kalman filter, residual calculation, Neural Networks
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
- G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
- G05B23/0259—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterized by the response to fault detection
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C5/00—Registering or indicating the working of vehicles
- G07C5/08—Registering or indicating performance data other than driving, working, idle, or waiting time, with or without registering driving, working, idle or waiting time
- G07C5/0808—Diagnosing performance data
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- General Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Operations Research (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Quality & Reliability (AREA)
- Mechanical Engineering (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Testing And Monitoring For Control Systems (AREA)
- Indication Of The Valve Opening Or Closing Status (AREA)
Abstract
The present invention relates to, to detect the unsupervised algorithm of the data-driven of abnormal valve operation, provide a method of computer implementation, system and computer program product for analyte sensors data.It identifies and multiple safeguards message (MMSG).Each MMSG is associated at least one shut-off valve.Analysis based on sensor parameters associated with the shut-off valve of each MMSG and identification sensor parameter.The threshold value of sensor parameters is identified as associated with the abnormal operation of corresponding shut-off valve.Sensor associated with the first shut-off valve captures the value of sensor parameters during the first time predefined section and the second time predefined section, and the first time predefined section and the second time predefined section are associated with the opening and closing of the first shut-off valve.When difference between the maximum value for determining the sensor values captured during the first time predefined section and the second time predefined section is more than first threshold, determine that the first shut-off valve operates singularly.
Description
Technical field
Various aspects described herein is related to the valve in aircraft, and more particularly relates to based on for analyzing sensing
The unsupervised algorithm of the data-driven of device data detects the method and system of abnormal valve operation.
Background technology
In general, the diagnosis of the abnormal operation of valve is difficult and time-consuming in aircraft.In addition, the target of conventional method is to examine
The abnormal operation of disconnected particular valve or certain types of valve.
Invention content
Message (MMSG) is safeguarded according on one side, a method of computer implementation includes that identification is multiple.Multiple MMSG
In each at least one of with multiple shut-off valves in the vehicles, shut-off valve is associated.This method further includes being based on
The analysis of associated at least one associated multiple sensor parameters of shut-off valve with each MMSG and identify the first sensing
Device parameter.In addition, the first threshold of first sensor parameter is identified as and the abnormal operation of corresponding at least one shut-off valve
It is associated.Period capture first senses first sensor associated with the first shut-off valve in multiple shut-off valves at the following time
Multiple values of device parameter:(i) the first time predefined section and (ii) second time predefined section, the first time predefined section and the
One corresponding in the opening and closing of the first shut-off valve of two time predefined sections are associated.Determining the first time predefined
The maximum value of multiple sensor values captured during section and the multiple sensor values captured during the second time predefined section
When difference between maximum value is more than the first threshold of first sensor parameter, determine that the first shut-off valve operates singularly.
According on one side, a kind of computer program product includes the meter of the computer-readable code with realization wherein
Calculation machine readable storage medium storing program for executing.Computer readable program code can be implemented to include identifying multiple to safeguard message to execute by processor
(MMSG) operation.Each in multiple MMSG shut-off valve phase at least one of with multiple shut-off valves in the vehicles
Association.The operation further includes being based on and the associated multiple sensor parameters of at least one shut-off valve associated with each MMSG
Analysis and identify first sensor parameter.In addition, the first threshold of first sensor parameter be identified as with it is corresponding at least
The abnormal operation of one shut-off valve is associated.Then first sensor associated with the first shut-off valve in multiple shut-off valves exists
Multiple values of first sensor parameter are captured during the following time:(i) when the first time predefined section and (ii) second are predefined
Between section, the first time predefined section and the second time predefined section phase corresponding in the opening and closing of the first shut-off valve
Association.The maximum value of the multiple sensor values captured during determining the first time predefined section in the second time predefined section
When difference between the maximum value of multiple sensor values of period capture is more than the first threshold of first sensor parameter, the is determined
One shut-off valve operates singularly.
According on one side, system includes computer processor and the memory comprising program.Program can be by processor reality
It includes the multiple operations for safeguarding message (MMSG) of identification to impose execution.In multiple MMSG each with it is more in the vehicles
At least one of a shut-off valve shut-off valve is associated.The operation further includes being based on and associated with each MMSG at least one
The analysis of the associated multiple sensor parameters of shut-off valve and identify first sensor parameter.In addition, first sensor parameter
First threshold is identified as associated with the abnormal operation of corresponding at least one shut-off valve.With first section in multiple shut-off valves
The only associated first sensor of valve and then at the following time multiple values of period capture first sensor parameter:(i) first is pre-
Period and (ii) second time predefined section are defined, the first time predefined section and the second time predefined section are ended with first
Corresponding one in the opening and closing of valve is associated.The multiple sensor values captured during determining the first time predefined section
Maximum value and the maximum value of the multiple sensor values captured during the second time predefined section between difference be more than first
When the first threshold of sensor parameters, determine that the first shut-off valve operates singularly.
Description of the drawings
Fig. 1 is to show to be driven with the data for detecting abnormal valve operation for analyte sensors data according to the realization of one side
The block diagram of the component of the system of dynamic unsupervised algorithm.
Fig. 2A -2B, which are shown, to be used for based on the data-driven for analyte sensors data according to various aspects without prison
Superintend and direct algorithm detect valve abnormal operation example technique.
Fig. 3 is the unsupervised algorithm based on the data-driven for analyte sensors data shown according to one side
Come detect valve abnormal operation method flow chart.
Fig. 4 is the method for showing the flying quality for analyzing the sensor in aircraft according to one side
Flow chart.
Fig. 5 is the method for showing the threshold value for being used to determine correlated variables and calculating correlated variables according to one side
Flow chart.
Fig. 6 is to show to determine flight based on the threshold value of data analysis, correlated variables and calculating according to one side
The flow chart for the method that first valve of device is operating singularly.
Fig. 7, which is shown, to be configured to based on the data-driven for analyte sensors data according to one side without prison
The system for superintending and directing algorithm to detect abnormal valve operation.
Specific implementation mode
Various aspects disclosed herein is provided using winged to detect with the n second windows of the relevant sensing data of shut-off valve
The technology of the failure of shut-off valve in row device (or other kinds of vehicles).The n second windows of sensing data are captured to be made
To parameterize a part for flying quality.In general, various aspects disclosed herein using unsupervised learning algorithm come analyze by
The data that sensor in previous flight provides are to identify that data value that instruction shut-off valve is operating singularly is (and associated
Parameter).Once identifying parameter and data value, then each side's surface analysis disclosed herein is opened and/or is closed in during flight valve
The n second windows of real-time flight data later.If the given valve of the n second windows instruction of real-time flight data is grasped singularly
Make, then various aspects disclosed herein can generate the instruction of abnormal operation.In some aspects, the instruction of abnormal operation is from aircraft
The receiving station being transferred on ground, at receiving station, maintenance crew and other staff are warned abnormal operation.For example, a side
Face, the instruction include just to order the request of replacing valve in the valve of abnormal operation.Doing so helps to actually occur failure in valve
Maintenance and repair aircraft before.
Because learning algorithm disclosed herein is data-driven, learning algorithm is model-free, and is not needed
The concrete condition of framework and schematic diagram for given aircraft is customized.In addition, learning algorithm is unsupervised, because of user
Manual creation labels for training data need not be intervened.Therefore, learning algorithm is in all types of aircraft, aircraft
All it is flexible and portable in system and subsystem component.Although aircraft used herein, which is used as, refers to example, this
It is open be equally applicable to include shut-off valve all types of vehicles.
Fig. 1 is to show to be driven with the data for detecting abnormal valve operation for analyte sensors data according to the realization of one side
The block diagram of the component of the system 100 of dynamic unsupervised algorithm.As shown, system 100 includes multiple aircraft subsystems
1011-N, computer 104 and multiple data storage devices 1101-N.Aircraft subsystem 1011-NRepresent son different in aircraft
System, and include multiple shut-off valves 1021-NWith multiple sensors 1031-N.Aircraft subsystem 1011-NExample include economy
Cooling valve (ECV) subsystem, environmental control system (ECS), fuel system, pneumatic system etc..As it is used herein, " cut-off
Valve " refers to the valve operated under one in two states (i.e. opening state and closed state).Shut-off valve 1021-NAdjust subsystem
System 1011-NIn air, the liquid of fuel or any other type or the flow of gas.Sensor 1031-NIt is the corresponding son of detection
System 1011-NIn condition, event and the physical equipment of variation, and generate for being stored in data storage device 1101-NIn
Corresponding data.Sensor 1031-NExample include temperature sensor, pressure sensor, airspeed sensor, humidity sensor,
Height sensor, etc..For example, if temperature sensor 1031In shut-off valve 102130 ° of air themperatures are detected when closing, then
Temperature sensor 1031Temperature reading is converted into number format, and the instruction of the temperature detected is transferred to data storage
Device 1101-NTo be stored in flying quality 111.
Data storage device 1101-NRepresent any kind of system of storage parametrization flying quality, such as flying quality
Logger (FDR), quickly access record (QAR), continuous parameter deposit system (CPL) and enhanced onboard flight logger
(EAFR).As shown, each data storage device 1101-NStorage device including flying quality 111 and safeguard message
(MMSG) 112 data storage device.Flying quality 111 stores the parametrization flight number for describing associated aircraft operation
According to.In general, parametrization flying quality is the set for the time series data collected during aircraft operation.Parametrization flies
The parameter of row data includes but not limited to the ginseng of height, the speed of aircraft, temperature data, pressure data for describing aircraft etc.
Number.More generally, the storage of flying quality 111 is by sensor 1031-NThe data value of the multiple parameters of generation, such as each shut-off valve
1021-NState (for example, open or closing) and other sampled values (temperature, pressure, moisture readings etc.).Extremely
In few one side, shut-off valve 1021-NTheir own state (for example, opening or closing) is transferred to flying quality
111。
In response to aircraft or the abnormal operation of its any part, the maintenance message being stored in MMSG 112 is generated.Example
Such as, sensor 103NRecord exemplary temperature threshold value more than 80 DEG C close to shut-off valve 102NIn one 100 DEG C of Air Temperature
Degree.In response, sensor 103NAnd/or the specified parts of aircraft generate MMSG based on the temperature recorded, then by it
It is stored in MMSG 112.Each MMSG112 with metadata parameters (such as corresponding timestamp), it is regular more than associated
One or more recording parameters (for example, temperature), aircraft impacted component (for example, one or more shut-off valve 1021-N)
Etc. it is associated.
As shown, computer 104 includes abnormal operation module 105 and threshold value 113.Abnormal operation module 105 be by with
It is set to detection shut-off valve 1021-NAbnormal operation application.Abnormal operation module 105 realizes unsupervised learning algorithm, analysis
Data storage device 1101-NHistory parameters flying quality in (for one or more aircraft), is cut with identifying and detecting
Only valve 1021-NIn the relevant sensor of abnormal behaviour 1031-NThe parameter of offer.In addition, abnormal operation module 105 is for each
The parameter of identification determines corresponding threshold value, the given shut-off valve 102 of threshold value instruction1-NOperate singularly (or will start
It operates singularly).Then the parameter identified and associated threshold value can be stored in threshold value 113 by abnormal operation module 105
In.Doing so allows abnormal operation module 105 to be analyzed in real time during (identical or other similar aircraft) subsequent flights
Data storage device 1101-N, and determine sensor 1031-NWhether the parameter that is identified more than corresponding threshold value is provided
Data value.If abnormal operation module 105 determines that the data value of identified threshold value has been more than corresponding threshold value, abnormal operation
Module 105 determines associated (one or more) shut-off valve 1021-NOperate singularly.Then, abnormal operation module 105
It generates and specifies shut-off valve 1021-NWhich of the instruction (for example, warning) that is operating singularly.In one aspect, the instruction
Including coming from data storage device 1101-NAssociated parametric data, reflect shut-off valve 1021-NGrasp singularly
Make.Do so the shut-off valve 102 by alerting related personnel's abnormal operation1-NTo promote safety, related personnel then can take suitable
When measure make a response.For example, maintenance crew can before aircraft lands orders for repairs and/or replace abnormal operation cut
Only valve 1021-NRequired part avoids delay so as to cause faster revolution and saves cost.
In one aspect, user defines the initial parameter collection for the input for being provided as abnormal operation module 105.Initial parameter
Collection includes the parameter from QAR, FDL, CPL and/or EAFR.For example, such parameter may include by sensor 1031-NIt measures
Temperature parameter, pressure parameter and flow parameter.In one aspect, user, which also defines, is provided as abnormal operation module 105
One or more mission phases of input.Example mission phase includes sliding, taking off, initially climbing, landing.In such side
Face, abnormal operation module 105 analyze parametrization flying quality 111 associated with specified mission phase, rather than for initial
All parametrization flying qualities of parameter set.
Abnormal operation module 105 executes the analysis of flying quality 111 to identify and determine shut-off valve 1021-NSingularly
Operate the subset of related initial parameter collection.In addition, abnormal operation module 105 calculates the threshold value of each parameter in subset.In this way
It does, abnormal operation module 105 determines previously when open and close given shut-off valve 102 based on flying quality 111N.It is general next
It says, flying quality 111 includes reflecting each shut-off valve 1021-NIn a corresponding record opened or closed.Then, abnormal behaviour
Make module 105 and is directed to shut-off valve 102NEach n for opening and closing event and obtaining the value for each parameter that initial parameter is concentrated
Second window.N seconds windows can be any length (60 seconds, 120 seconds etc.), and can be specified by user, or different
The predefined value encoded in normal operation module 105.Then abnormal operation module 105 is known for each parameter that initial parameter is concentrated
Not in the maximum value of each n seconds interim.Then abnormal operation module 105 calculates for each variable and opens shut-off valve 102N
The maximum value and close identical shut-off valve 102 next time that the n seconds later are spacedNBetween the maximum value of n second windows later
Difference.
Fig. 2A shows the curve graph 200 generated from the exemplary temperature value being stored in flying quality 111.Curve graph 200
Y-axis correspond to by with shut-off valve 102NAssociated sensor 103NThe temperature parameter (for example, being concentrated in initial parameter) of record
Temperature value.The x-axis of curve graph joins with time correlation.As shown, working as shut-off valve 102NWhen being opened at 0 second, temperature value is about
It is 155 DEG C.The maximum value for being spaced (being in this example 120 seconds) is present in about 169 DEG C of point 201 within n seconds.It is closed next time
Close shut-off valve 102NLater, occurs about 174 degrees Celsius of maximum observed temperature at point 202.Therefore, for shown in Fig. 2A
Shut-off valve 102NOpening event and close event, the maximum in 120 seconds windows each of is calculated by abnormal operation module 105
Difference between temperature value is about 5 DEG C (for example, 174-169=5).For the sake of clarity, the difference between maximum parameter value
Referred to herein as " max_diff " value.
Abnormal operation module 105 calculates each parameter and given shut-off valve 102 that initial parameter is concentratedNEach opening
With the max_diff values of closing.Then abnormal operation module 105 executes further analysis to identify and given shut-off valve 102N
(and similar or identical shut-off valve 1021-N) the associated initial parameter collection of abnormal operation subset.In general, abnormal
Operation module 105 calculates the correspondence percentile of the max_diff values each calculated for each parameter that initial parameter is concentrated
(percentile) threshold value.In one aspect, which is the three of the max_diff values of the calculating of associated parameter
A standard deviation.Continue temperature example shown in Fig. 2A, 21 degree of example percentile threshold value is calculated by abnormal operation module 105
Max_diff values, wherein 21 degree indicate for temperature parameter calculate all max_diff values the 95th percentile (or three mark
Quasi- deviation).
Then abnormal operation module 105 identifies the max_diff values calculated more than each of percentile threshold value.For example, abnormal
Operation module 105 is for exemplary temperature parameter shown in Fig. 2A respectively at Exemplary temporal t=1, t=2, t=3 and t=4
The temperature max_diff values of 22,23,24 and 25 degree of identification.In order to identify instruction shut-off valve 1021-NThe threshold operated singularly
Value max_diff threshold values, then abnormal operation module 105 steps through each max_diff values with 0.1 increment, until reaching
Maximum max_diff values (for example, the 100th percentile of max_diff values).
For each max_diff values, abnormal operation module 105 identify in MMSG 112 with shut-off valve 1021-NIt is associated
MMSG.For the MMSG that each of MMSG 112 is identified, abnormal operation module 105 calculates the false positive and kidney-Yang of current MMSG
The ratio of property.Do so, abnormal operation module 105 determine current max_diff values whether appear in current max_diff values when
Between time predefined section in (for example, in 7 days, in 14 days, in 24 days, etc.).Therefore, continue the temperature example of Fig. 2A, such as
The current max_diff values of fruit are 23, then abnormal operation module 105 determines whether current MMSG appears in 24 days of time t=2.
If current max_diff values appear in time predefined section, abnormal operation module 105 thinks that current max_diff values are
True positives.Otherwise, current max_diff values are considered as false positive by abnormal operation module 105.In general, abnormal operation mould
Block 105 is for each max_diff values (for example, 22.0,22.1,22.2 ..., 24.8,24.9,25.0) calculating false positive and very
Positive ratio.Then abnormal operation module 105 defines the threshold value of the parameter.In one aspect, abnormal operation module 105 is by threshold
Value is defined as the max_diff values with the ratio of the minimum calculating of false positive and true positives.For example, if for 22.2 meters
The ratio of calculation is minimum in calculated ratio, then in these aspects, abnormal operation module 105 is defined as temperature by 22.2
The threshold value of parameter.On the other hand, abnormal operation module 105 by threshold definitions be with shut-off valve 1021-NIt is associated every
The max_diff values occurred in the time predefined section of the MMSG of a identification.For example, if occurring in 24 days of each MMSG
22.5 max_diff values, then in these areas, the threshold value that abnormal operation module 105 is defined as temperature parameter by 22.5.It is abnormal
Then the instruction of threshold value and parameter is stored in threshold value 113 by operation module 105.It does so including the son as initial parameter collection
The parameter of the member of collection.
Fig. 2 B show that according to one side include max_diff temperature values of calculating as y-axis and as x-axis
The curve graph 250 of time.As shown, curve graph 250 includes the example threshold calculated as described above by abnormal operation module 105
Max_diff values 251.As shown, threshold value max_diff values 251 are about 19 degree.In addition, curve graph 250 includes vertical line
Each in 252-256, vertical line 252-256 corresponds to a MMSG in MMSG 112.In addition, example max_diff values
261-266 is labeled in curve graph 250, to notice the degree of approach of each MMSG lines 252-256.As previously mentioned, at one
Aspect, abnormal operation module 105 calculate threshold value 251 as the lowest ratio with false positive and true positives (based on given MMSG
The temporal degree of approach) associated value.For example, if abnormal operation module 105 detects that a false positive and ten are true
The positive, the then ratio calculated are 0.1.On the other hand, abnormal operation module 105 is based on the given MMSG 252- of capture
The max_diff values of 256 all MMSG define threshold value 251 (for example, each example of max_diff values more than threshold value exists
In predefined period (for example, 24 days)).
Some parameters are not off valve 1021-NThe good indicator of failure and/or abnormal operation.Abnormal operation module 105
These parameters are abandoned, because these parameters do not have and any associated max_diff values of (or considerably less) true positives usually.
Therefore, the ratio of false positive and true positives is no definition (due to division by 0) or very big.In this way, abnormal operation module
105 abandon any such parameter.For example, in one aspect, abnormal operation module 105 abandons the ratio of its false positive and true positives
Rate is more than the parameter of relevance threshold or its ratio without those of definition parameter.Therefore, abnormal operation module 105 is by initial parameter
It is to be associated with reflected shut-off valve by these values and the MMSG in MMSG 112 that the subset of collection, which is defined as its max_diff value,
1021-NAbnormal operation the reason of those of parameter.
Once abnormal operation module 105 has identified the subset of parameter and corresponding threshold value, then abnormal operation module 105
With regard to determining whether the flying quality 111 captured in real time in during flight reflects shut-off valve using the subset and corresponding threshold value
1021-NOperate singularly.In general, during flight (or one in the predefined stage of flight), sensor
1031-NThere is provided parametrization flying quality to flying quality 111.Whenever shut-off valve 1021-NWhen opening or closing, abnormal operation mould
Block 105 is just for the n second windows of the parameter identification parameter flying quality in the subset of parameters defined in threshold value 113.Then different
Normal operation module 105 is calculated after opening and closing (or close and open) in the subset of parameters for each n seconds window
The max_diff values of each parameter.In one example, abnormal operation module 105 is based on by sensor 1031-NThe data of capture
N seconds window calculation max_diff temperature value, pressure value etc..If the max_diff values calculated are more than corresponding threshold value, different
Normal operation module 105 determines corresponding shut-off valve 102NOperate singularly.Continue previous temperature example, if abnormal behaviour
Make module 105 and calculate the max_diff that temperature parameter is 28 degree, then abnormal operation module 105 is determined as 28 max_diff
The example threshold that it is 19 degree that value, which has been more than shown in Fig. 2 B,.In this way, abnormal operation module 105 determines associated shut-off valve
102NOperate (or faulty) singularly.In one aspect, then abnormal operation module 105 generates and specifies shut-off valve 102N
Faulty instruction.In one aspect, the instruction from aircraft is transferred to remote system by abnormal operation module 105, is permitted
Perhaps maintenance crew obtains renewal part, place under repair etc..
However, in some respects, the computer 104 that executes abnormal operation module 105 be (for example, via network connection) from
Multiple and different aircraft receives the external system of flying quality 111 and MMSG 112.Therefore, in such embodiments, work as knowledge
It is different when relevant parameter and determining reflection in other subset of parameters give the associated threshold value that shut-off valve is operating singularly
Normal operation module 105 utilizes flying quality 111 and MMSG 112 from these different aircraft.At such aspect, remote
The abnormal operation module 105 executed on journey computer 104 can receive the real-time flight data from multiple and different aircraft, and
And determine whether given aircraft has the shut-off valve 102 operated singularlyN。
Fig. 3 is shown according to one side for based on the unsupervised of the data-driven for analyte sensors data
Algorithm detects the flow chart of the method 300 of the abnormal operation of shut-off valve.As shown, method 300 starts at frame 310,
Middle user defines initial parameter collection and any applicable mission phase.Do so allow abnormal operation module 105 be stored in it is winged
It is operated on the initial subset of thousands of or millions of a parameters in row data 111.At frame 320, abnormal operation module 105 receives
Parameterize flying quality 111.As it was earlier mentioned, parametrization flying quality 111 is by shut-off valve 1021-NWith sensor 1031-NIt generates.
In general, the flying quality 111 of reception is reflected in the flying quality 111 captured on multiple flight legs.In at least one side
Face, the flying quality 111 of reception further reflect the flying quality 111 captured by multiple aircraft.
At the frame 330 being more fully described with reference to figure 4, abnormal operation module 105 analyzes flying quality.In general,
At frame 330, abnormal operation module 105 calculates the max_diff values of parameter in flying quality 111.At frame 340, a side
It occurs parallel with frame 330 in face, and abnormal operation module 105 identifies the target MMSG in MMSG 112.In general, target MMSG
It is and shut-off valve 1021-NThose associated MMSG of abnormal operation.It is abnormal to grasp at reference to figure 5 in greater detail frame 350
Make module 105 to determine and detection shut-off valve 1021-NIn the related initial parameter collection of abnormal behaviour subset, and calculating parameter
The threshold value of each parameter in subset.
At the frame 360 being more fully described with reference to figure 6, abnormal operation module 105 be based on data analysis, subset of parameters and
The threshold value of subset of parameters determines the first shut-off valve 102NOperate singularly.In general, at frame 360, abnormal operation mould
Block 105 analyzes real-time flight data to determine shut-off valve 102NOperate singularly.For example, if the temperature ginseng of turbine inlet
Several threshold value max_diff values are 40 degree, then abnormal operation module 105 can enter for the given turbine in period that opens/closes
The max_diff of mouth determines corresponding shut-off valve 102 when being 50 degreeNOperate singularly.At frame 370, abnormal operation module
105 generate and transmit specified first shut-off valve 102NThe instruction operated singularly.
Fig. 4 is the flying quality corresponded to for analyzing the sensor in aircraft shown according to one side
The flow chart of the method 400 of frame 330.As shown, method 400 starts at frame 410, wherein user is optionally defined on cut-off
Valve 102NThe time interval (for example, 120 seconds) of the n second windows of the parametrization flying quality of opening and/or the post analysis of closing.So
And At at least one aspect, n seconds time intervals are the predefined values in abnormal operation module 105.At frame 415, abnormal operation
Module 105 is directed to each shut-off valve 102 existing for the data in flying quality 1111-NExecution includes the cycle of frame 420-460.
At frame 420, abnormal operation module 105 determines reflection current expiration valve 102NThe flying quality 111 opened and closed every time in
Time index.At frame 425, abnormal operation module 105 includes frame 430-455 for each determining time index execution
Cycle.
At frame 430, abnormal operation module 105 is received for each parameter that initial parameter is concentrated from flying quality 111
The data of the time interval (for example, 120 seconds) of definition.For example, abnormal operation module 105 can receive temperature parameter and association
Value, pressure parameter and relating value, height parameter and relating value etc..At frame 440, abnormal operation module 105 is directed to initial parameter
The each parameter execution concentrated includes the cycle of frame 440-450.At frame 440, current time is indexed (for example, beating ON/OFF
Close or the close/open period), abnormal operation module 105 determines the current ginseng in the n second windows of data after the opening and closing
Several maximum values.For example, abnormal operation module 105 can be in current expiration valve 102NIt was identified as in window at n seconds after opening
210 degree of maximum temperature values, and in current expiration valve 102N140 degree of maximum temperature was identified as at n seconds after closing in window
Angle value.At frame 445, abnormal operation module 105 calculates the difference between the maximum value determined at frame 450.In other words, different
Normal operation module 105 calculates the max_diff values of parameter current and time index.Continue the example of front, abnormal operation module
105 will be calculated as the max_diff values of 210-140=70 degree for Current Temperatures parameter and time index.In one aspect, different
Normal operation module 105 stores the max_diff values calculated for using later.
At frame 450, abnormal operation module 105 is determined in the whether remaining more parameters of initial parameter concentration.If remaining
More parameters, then abnormal operation module 105 return to frame 435.Otherwise, abnormal operation module 105 proceeds to frame 455.In frame 455
Place, abnormal operation module 105 determine whether remaining more time indexs.If remaining more time indexs, abnormal to grasp
Make module 105 and return to frame 425, otherwise, abnormal operation module 105 proceeds to frame 460.At frame 460, abnormal operation module
105 determine whether remaining more shut-off valves 1021-N.If it is, abnormal operation module 105 returns to frame 415.Otherwise, side
Method 400 terminates.
Fig. 5 is to show corresponding to for determining correlated variables and calculating the threshold value of correlated variables according to one side
The flow chart of the method 500 of frame 350.As shown, method 500 starts at frame 505, wherein user optionally defines max_
The percentile threshold value (for example, two standard deviations) of diff values.However, At at least one aspect, in abnormal operation module 105
Predefined percentile threshold value.At frame 510, abnormal operation module 105 includes for each parameter execution that initial parameter is concentrated
The cycle of frame 515-565.At frame 515, abnormal operation module 105 is directed to the current ginseng more than the threshold value defined at frame 510
Each of several max_diff values execution calculated include the cycle of frame 520-555.At frame 520, abnormal operation module 105 is directed to
Each MMSG execution in the MMSG 112 identified at frame 340 includes the cycle of frame 525-530.
At frame 525, abnormal operation module 105 determines that current MMSG 112 relative to current max_diff values is false positive
Or true positives.In general, it does so, abnormal operation module 105 determines whether current MMSG 112 appears in current max_
In the time predefined section (for example, 24 days) of diff values.For example, if current MMSG 112 appears on January 25th, 2017,
And observe current max_diff values on January 24th, 2017, then abnormal operation module 105 determines that MMSG 112 is kidney-Yang
Property.At frame 530, abnormal operation module 105 determines whether remaining more MMSG.If remaining more MMSG, abnormal
Operation module 105 returns to frame 520.Otherwise, abnormal operation module 105 proceeds to frame 535.
At frame 535, abnormal operation module 105 calculates the ratio of the false positive and true positives of parameter current.In frame 540
Place, abnormal operation module 105 determine whether the ratio calculated at frame 535 is less than current minimum rate.If counted at frame 535
The ratio of calculation is not less than current minimum rate (or without definition), then abnormal operation module 105 proceeds to frame 550.However, if
The ratio calculated at frame 535 is less than current minimum rate (and not without definition), then abnormal operation module 105 proceeds to frame
545, wherein abnormal operation module 105 sets the ratio calculated at frame 535 to current minimum rate, and by current minimum
Ratio is associated with current max_diff values.
At frame 550, abnormal operation module 105 is incremented by the current value of the max_diff values of parameter current.For example, at one
Aspect, as described above, the max_diff values of parameter current are incremented by 0.1 by abnormal operation module 105, until analyzing maximum max_
Diff values.At frame 555, abnormal operation module 105 determines whether remaining more max_diff values.If remaining more max_
Diff values, then method is back to frame 515, and otherwise, abnormal operation module 105 proceeds to frame 560.At frame 560, abnormal operation mould
Max_diff values associated with the minimum rate of false positive and true positives are stored as parameter current in threshold value 113 by block 105
Threshold value.Do so the member for the subset that parameter current is defined as to initial parameter collection, for example, with detection shut-off valve 1021-NIn event
Hinder relevant parameter.However, if without minimum rate, abnormal operation module 105 abandons incoherent parameter current.In frame
At 565, abnormal operation module 105 is determined in the whether remaining more parameters of initial parameter concentration.If remaining more parameters, different
Normal operation module 105 returns to frame 510, and otherwise, method 500 terminates.
Fig. 6 is to show to correspond to the threshold value based on data analysis, correlated variables and calculating according to one side come really
Determine the flow chart of the method 600 for the frame 360 that the first valve of aircraft is operating singularly.In general, abnormal operation module
105 execute method 600, to determine whether real-time flight data 111 is indicated to based on the training data being stored in threshold value 113
Determine shut-off valve 102NWhether operated singularly in during flight.As shown, method 600 starts at frame 610, it is different at this
Normal operation module 105 is for each shut-off valve 102 in aircraftNExecution includes the cycle of frame 620-690.
At frame 620, abnormal operation module 105 is determining current expiration valve 102NIt receives and comes from when having already turned on or closing
The parametric data of flying quality 111.For example, abnormal operation module 105 can receive temperature data, pressure data, the high number of degrees
According to etc., wherein passing through sensor 1031-NGenerate data.In addition, the data received from flying quality 111, which are limited in, beats on and off
Close shut-off valve 102NN second windows later.At frame 630, abnormal operation module 105 is for the parameter defined in threshold value 113
Each parameter execution in subset includes the cycle of frame 640-680.At at least one aspect, the parameter in subset of parameters with it is current
Shut-off valve 102N(or substantially similar shut-off valve) is associated.
At frame 640, abnormal operation module 105 is in shut-off valve 102NIt determines after opening and closing and is received at frame 620
Flying quality n second windows in parameter current maximum value.At frame 650, abnormal operation module 105 is calculated in frame 640
Locate the difference between the maximum value of identification.In other words, abnormal operation module 105 calculates the max_diff values of parameter current.
At frame 660, abnormal operation module 105 determine at frame 650 calculate max_diff values whether be more than parameter current threshold value
(as defined in threshold value 113).If max_diff values have been more than threshold value, abnormal operation module 105 proceeds to frame 670,
Otherwise, abnormal operation module 105 proceeds to frame 680.At frame 670, max_diff of the abnormal operation module 105 based on calculating is super
It crosses corresponding threshold value and determines current expiration valve 102NOperate singularly.At frame 680, the determination of abnormal operation module 105 is
No residue more parameters.If remaining more parameters, abnormal operation module 105 return to frame 630, otherwise, abnormal operation mould
Block 105 proceeds to frame 690.At frame 690, abnormal operation module 105 determine aircraft in whether remaining more shut-off valves
1021-N.If it is, abnormal operation module 105 returns to frame 610, otherwise, method 600 terminates.
Fig. 7, which is shown, to be configured to based on the data-driven for analyte sensors data according to one side without prison
Algorithm is superintended and directed to detect the system 700 of abnormal valve operation.Networked system 700 includes computer 104.Computer 104 also can be via net
Network 730 is connected to other computers.In general, network 730 can be telecommunication network and/or wide area network (WAN).Specific real
It applies in example, network 730 is internet.
Computer 104 generally includes processor 704, and processor 704 is via bus 720 from memory 706 and/or reservoir
708 obtain instruction and data.Computer 104 can also include the one or more network interface devices for being connected to bus 720
718, input equipment 722 and output equipment 724.Computer 104 is usually under the control of operating system (not shown).Operating system
Example include UNIX operating system, the version of Microsoft Windows operating systems and (SuSE) Linux OS point
Cloth.(UNIX is registered trademarks of the The Open Group in the U.S. and other countries.Microsoft and Windows are
Trade marks of the Microsoft Corporation (Microsoft) in the U.S., other countries or both.Linux is Linus
Registered trademarks of the Torvalds in the U.S., other countries or both.) more generally, it can use and support function disclosed herein
Any operating system.Processor 704 be execute instruction, the programmable logic device of logic and Mathematical treatment, and can represent
One or more CPU.Network interface device 718 can be that computer 104 is allowed to be communicated with other computers via network 730
Any kind of network communication equipment.
Reservoir 708 represents hard disk drive, solid state drive, flash memory device, optical medium etc..In general, it stores
Device 708 stores the application program and data used by computer 104.In addition, memory 706 and reservoir 708 can be considered wrapping
Include the memory for being physically located at other places;Such as it is coupled on another computer of computer 104 via bus 720.
Input equipment 722 can be any equipment for providing input to computer 104.For example, can be used keyboard and/
Or mouse.Input equipment 722 represents various input equipments comprising keyboard, mouse, controller etc..In addition, input
Equipment 722 may include the one group of button, switch or other physical equipment mechanisms for control computer 104.Output equipment 724
It may include the output equipment of monitor, touch-screen display etc..
As shown, memory 706 includes abnormal operation module 105, and reservoir 708 includes flying quality 111, MMSG
112 and threshold value 113.In general, system 700 is configured to realize the repertoire above with reference to described in Fig. 1-6.
As shown, system 700 further includes multiple aircraft 7501-NAnd it is communicatively coupled to count via network 730
The maintenance system 760 of calculation machine 1041-N.As shown, aircraft 7501-NIncluding multiple shut-off valves 1021-N, multiple sensors
1031-N, flying quality 111 and MMSG 112.At at least one aspect, given aircraft 7501-NUsing aircraft communication and
Addressing reporting system (ACARS) is communicated by network.As shown, maintenance system 7601-NIncluding message recipient 777,
Message recipient 777 is configured to receive in aircraft 750 from abnormal operation module 1051-NMiddle abnormal operation shut-off valve 1021-N
Instruction.
For example, in one aspect, message recipient 777 receives the one or more cut-offs of instruction from abnormal operation module 105
Valve 1021-NIn one or more aircraft 7501-NIn the alert message that operates singularly.In one aspect, disappear in response to warning
Breath, message recipient 777 arrange corresponding aircraft 750NMaintenance.In addition, message recipient 777 automatically orders replacement zero
Part is to repair faulty shut-off valve 1021-N.In addition, message recipient 777 exports alert message to skilled worker for checking, from
And allow skilled worker's schedule maintenance (including checking whether message recipient 777 has ordered part appropriate automatically).In some respects,
When aircraft 750NWhen landing, skilled worker can fix faulty shut-off valve 1021-N。
Advantageously, various aspects disclosed herein are provided determines that shut-off valve is faulty based on unsupervised learning algorithm
Or the technology that operates singularly.Unsupervised learning algorithm is model-free, and includes identification relevant parameter and corresponding threshold
The study stage of value.Then the data generated during the study stage are used for analyzing real-time flight data.If real-time flight number
According to including value more than given threshold value, then various aspects disclosed herein determine associated shut-off valve singularly operation or
It is faulty.
In foregoing teachings, with reference to the various aspects presented in the disclosure.However, the scope of the present disclosure is not limited to specifically describe
Various aspects.On the contrary, regardless of whether be related to different aspect, any combinations of the feature and element be all considered for realizing and
The expected aspect of practice.Although possible solution better than other or better than existing in addition, various aspects disclosed herein can be realized
There is the advantages of technology, but whether realizes that specific advantages are not intended to limit the scope of the present disclosure by given aspect.Therefore, cited
Aspect, feature, aspect and advantage be merely illustrative, and be not considered as element or the limitation of appended claims,
Unless clearly stating in the claims.Similarly, disclosed herein is not necessarily to be construed as to the reference of " present invention "
The summary of what subject matter, and it is not considered as element or the limitation of appended claims, unless bright in the claims
Really statement.
Various aspects described herein can take complete hardware in terms of, it is (including firmware, resident soft in terms of complete software
Part, microcode etc.) or integration software in terms of and hardware aspect aspect form, these aspect herein usually all can quilt
Referred to as circuit, " module " or " system ".
Various aspects can be system, method and/or computer program product.Computer program product may include having thereon
Be useful for making processor carry out the computer-readable program instructions of various aspects described herein computer readable storage medium (or
Multiple media).
Computer readable storage medium can be can retain and store the instruction used by instruction execution equipment tangible
Equipment.Computer readable storage medium can be such as but not limited to electronic storage device, magnetic storage apparatus, light storage device,
Electromagnetism storage device, semiconductor memory apparatus or any suitable combination above-mentioned.Computer readable storage medium it is more specific
Exemplary non-exhaustive list includes following items:Portable computer diskette, random access memory (RAM), read-only is deposited hard disk
Reservoir (ROM), Erasable Programmable Read Only Memory EPROM (EPROM or flash memory), static RAM (SRAM),
Portable optic disk read-only storage (CD-ROM), digital versatile disc (DVD), memory stick, floppy disk, the equipment mechanically encoded
(such as record has card punch or bulge-structure in the groove of instruction thereon) and any suitable combination above-mentioned.Herein
The computer readable storage medium used is not necessarily to be construed as temporary signal itself, such as radio wave or other Free propagations
Electromagnetic wave, the electromagnetic wave (for example, the light pulse for passing through fiber optic cables) propagated by waveguide or other transmission mediums or by leading
The electric signal of line transmission.
Computer-readable program instructions described herein can be downloaded to from computer readable storage medium corresponding calculating/
Processing equipment, or download to outer computer via network (such as internet, LAN, wide area network and/or wireless network)
Or External memory equipment.Network may include copper transmission cable, optical delivery fiber, wireless transmission, router, fire wall, interchanger,
Gateway computer and/or Edge Server.Adapter or network interface in each calculating/processing equipment are received from network
Computer-readable program instructions, and computer-readable program instructions are forwarded to be stored in corresponding calculating/processing equipment
Computer readable storage medium in.
Computer-readable program instructions for carrying out operation described herein can be assembly instruction, instruction set architecture
(ISA) instruction, machine instruction, machine-dependent instructions, microcode, firmware instructions, condition setup data or with one or more volumes
Cheng Yuyan (programming language of the object-oriented including Smalltalk, C++ etc. and such as " C " programming language or similar volume
The conventional procedural programming language of Cheng Yuyan) any combinations write-in source code or object code.Computer-readable program refers to
Enable can completely on the user computer, part on the user computer, as independent software package, part on the user computer simultaneously
And part executes on a remote computer or server on the remote computer or completely.In the latter case, long-range meter
Calculation machine can by including any kind of network connection of LAN (LAN) or wide area network (WAN) to the computer of user, or
It may be connected to outer computer (for example, by using internet of Internet Service Provider).In some respects, including for example
The electronic circuit of programmable logic circuit, field programmable gate array (FPGA) or programmable logic array (PLA) can pass through profit
Computer-readable program instructions are executed with individual electronic circuit, to hold with the status information of computer-readable program instructions
Row various aspects described herein.
Herein with reference to the flow chart according to method, apparatus (system) and computer program product of aspects described herein
Diagram and/or block diagram describe various aspects.It should be appreciated that by computer-readable program instructions may be implemented flow chart and/or
The combination of each frame in block diagram and the frame in flowchart and or block diagram.
These computer-readable program instructions can be provided to all-purpose computer, special purpose computer or other programmable numbers
According to the processor of processing unit to generate machine so that held via the processor of computer or other programmable data processing units
Capable instruction creates for realizing the device for the function action specified in one or more frames of flowchart and or block diagram.This
A little computer-readable program instructions are also stored in computer readable storage medium, which can refer to
It leads computer, programmable data processing unit and/or other equipment to run in a specific way so that be wherein stored with the meter of instruction
Calculation machine readable storage medium storing program for executing includes manufacture article comprising realizes and is specified in one or more frames of flowchart and or block diagram
Function action various aspects instruction.
Computer-readable program instructions can also be loaded into computer, other programmable data processing units or other equipment
On, so that executing series of operation steps in computer, other programmable devices or other equipment to generate computer reality
Existing process so that the instruction executed in computer, other programmable devices or other equipment is realized in flow chart and/or frame
The function action specified in one or more frames of figure.
Flowcharts and block diagrams in the drawings show according to the system of various aspects described herein, method and computer journey
The framework of the possible embodiment of sequence product, function and operation.In this regard, each frame in flowchart or block diagram can indicate
Include module for realizing the instruction of one or more executable instructions of specified (one or more) logic function, section
Or part.In some alternative embodiments, the function of being mentioned in frame can not occur according to the sequence marked in attached drawing.
For example, according to involved function, two frames continuously shown actually can be executed substantially simultaneously or frame sometimes can be with
Opposite sequence executes.In each frame and block diagram and or flow chart that are also noted that in block diagram and or flow chart
The combination of frame can be executed by the system based on specialized hardware, system based on specialized hardware execute specified function or action or
Implement the combination of specialized hardware and computer instruction.
Aspects described herein can be provided to terminal user by cloud computing infrastructure.Cloud computing typically refers to
Expansible computing resource, which is provided, by network is used as service.More formally, cloud computing can be defined as in computing resource and its
Abstract computing capability is provided between floor layer technology framework (for example, server, reservoir, network), enabling is easily pressed
It needs network to access shared configurable computing resource pond, minimum management work or service provider's interaction can be used quickly to supply
It should and issue.Therefore, cloud computing allow user access " cloud " in virtual computing resource (for example, reservoir, data, using journey
Sequence and even complete virtualized computing system), without consider for provide computing resource underlying physical system (or these
The position of system).
In general, cloud computing resources are supplied to user based on pay-per-use (pay-per-use), wherein only for reality
The computing resource that border uses is (for example, the amount for the memory space that user is consumed or the multiple virtualizations instantiated by the user
System) it charges to user.User can access any resource in cloud at any time and from anywhere on internet.
In the context of at least one aspect, user may have access to available application program or related data in cloud.For example, abnormal operation mould
Block 105 can be executed in the computing system in cloud and associated threshold value in the subset of defined parameters and threshold value 113.It does so
Allow user or application program from being attached to any computing system accesses of network (for example, internet) letter for being connected to cloud
Breath.
The description of various aspects has been presented for purposes of illustration, it is not intended that exhaustive or be limited to disclosed
Aspect.Without departing from the scope and spirit of described various aspects, many modifications and variations are for this field
It will be apparent for those of ordinary skill.Selection in terms used herein is better than in market to best explain
Principle, practical application or the technological improvement of the various aspects of the technology of middle discovery, or enable those skilled in the art
Understand various aspects disclosed herein.
In addition, the disclosure includes according to following clause the embodiment described:
1. a method of computer implementation of clause comprising:
Identify it is multiple safeguard message (MMSG), each in multiple MMSG in multiple shut-off valves in the vehicles extremely
Few shut-off valve is associated;
Based on the analysis of associated at least one associated multiple sensor parameters of shut-off valve with each MMSG
It identifies the first sensor parameter in the multiple sensor parameters, and the first threshold of the first sensor parameter is known
It Wei not be associated with the corresponding abnormal operation of at least one shut-off valve;
By first sensor associated with the first shut-off valve in the multiple shut-off valve, period catches at the following time
Obtain multiple values of the first sensor parameter:(i) the first time predefined section and (ii) second time predefined section, wherein institute
It states the first time predefined section and the second time predefined section is corresponding in the opening and closing of first shut-off valve
One associated;And
In the maximum value of the determining the multiple sensor values captured during the first time predefined section and in institute
It is more than first biography to state the difference between the maximum value of the multiple sensor values captured during the second time predefined section
When the first threshold of sensor parameter, determine that first shut-off valve operates singularly.
Computer implemented method of the clause 2. according to clause 1 further include:
Generate the warning instruction for specifying the first shut-off valve operating singularly;
Warning instruction is transferred to remote computing device via network;
The warning instruction is received by the message recipient of the remote computing device;And
The maintenance of first shut-off valve is arranged by described information receiver.
Computer implemented method of the clause 3. according to any one of clause 1-2, wherein described first is predefined
Period and the second time predefined section have first time length, wherein the analysis of the multiple sensor parameters is based on
The value of the multiple sensor parameters previously collected, wherein the analysis bag includes:
Identification the multiple sensor associated with multiple opening and closing of each in the multiple shut-off valve
The value of parameter previously collected, wherein the value previously collected be identified as corresponding shut-off valve it is each opening and
Occur in the first time length after closing every time;And
For each sensor parameters in the multiple sensor parameters, each sensor for opening every time is calculated
The maximum value of phase between the maximum value of parameter and to(for) each sensor parameters of corresponding shut-off valve closed every time
Answer difference.
Computer implemented method of the clause 4. according to clause 3, wherein the analysis further includes:
For each sensor parameters in the multiple sensor parameters, standard in each of the difference based on calculating
Deviation is calculated for the first percentile threshold value in multiple percentile threshold values of the difference of the calculating;And
Determine the difference each calculated associated with the first sensor parameter more than the first percentile threshold value
It is worth and occurs in the time close with one time in the MMSG.
Computer implemented method of the clause 5. according to clause 4, wherein the analysis further includes:
Determine the second percentile threshold value in the multiple percentile threshold value of the first sensor parameter with than other
Each lesser amount of false positive MMSG in multiple threshold values is associated;And
By the first threshold that the second percentile threshold definitions are the first sensor parameter.
Computer implemented method of the clause 6. according to clause 5, wherein the first percentile threshold value is less than described
Each in other percentile threshold values, wherein the first percentile threshold value include in the multiple sensor parameters
Three associated values of standard deviation of the difference of the calculating of each.
Method of the clause 7. according to any one of clause 1-6, wherein based on every in the multiple MMSG of determination
One corresponding date appears in third time predefined section and identifies the multiple MMSG.
A kind of 8. system of clause comprising:
One or more computer processors;And
Memory, it includes program, described program executed when being implemented by processor include following items operation:
Identify it is multiple safeguard message (MMSG), each in multiple MMSG in multiple shut-off valves in the vehicles extremely
Few shut-off valve is associated;
Based on the analysis of associated at least one associated multiple sensor parameters of shut-off valve with each MMSG
It identifies the first sensor parameter in the multiple sensor parameters, and the first threshold of the first sensor parameter is known
It Wei not be associated with the corresponding abnormal operation of at least one shut-off valve;
By first sensor associated with the first shut-off valve in the multiple shut-off valve, period catches at the following time
Obtain multiple values of the first sensor parameter:(i) the first time predefined section and (ii) second time predefined section, wherein institute
It states the first time predefined section and the second time predefined section is corresponding in the opening and closing of first shut-off valve
One associated;And
In the maximum value of the determining the multiple sensor values captured during the first time predefined section and in institute
It is more than first biography to state the difference between the maximum value of the multiple sensor values captured during the second time predefined section
When the first threshold of sensor parameter, determine that first shut-off valve operates singularly.
System of the clause 9. according to clause 8, the operation further include:
Generate the warning instruction for specifying the first shut-off valve operating singularly;
Warning instruction is transferred to remote computing device via network;
The warning instruction is received by the message recipient of the remote computing device;And
The maintenance of first shut-off valve is arranged by described information receiver.
System of the clause 10. according to any one of clause 8-9, wherein the first time predefined section and described
Two time predefined sections have first time length, wherein the analysis of the multiple sensor parameters is based on the multiple sensor
The value of parameter previously collected, wherein the analysis bag includes:
Identification the multiple sensor associated with multiple opening and closing of each in the multiple shut-off valve
The value of parameter previously collected, wherein the value previously collected be identified as corresponding shut-off valve it is each opening and
Occur in the first time length after closing;And
For each sensor parameters in the multiple sensor parameters, each sensor for opening every time is calculated
The maximum value of phase between the maximum value of parameter and to(for) each sensor parameters of corresponding shut-off valve closed every time
Answer difference.
System of the clause 11. according to clause 10, wherein the analysis further includes:
For each sensor parameters in the multiple sensor parameters, in each of the difference based on the calculating
Standard deviation is calculated for the first percentile threshold value in multiple percentile threshold values of the difference of the calculating;And
Determine the difference each calculated associated with the first sensor parameter more than the first percentile threshold value
It is worth and occurs in the time close with one time in the MMSG.
System of the clause 12. according to any one of clause 8-11, wherein the analysis further includes:
Determine the second percentile threshold value in the multiple percentile threshold value of the first sensor parameter with than other
Each lesser amount of false positive MMSG in multiple threshold values is associated;And
By the first threshold that the second percentile threshold definitions are the first sensor parameter.
System of the clause 13. according to clause 12, wherein the first percentile threshold value is less than other described percentiles
Each in threshold value, wherein the first percentile threshold value includes and the institute for each in the multiple sensor parameters
State three associated values of standard deviation of the difference of calculating.
System of the clause 14. according to any one of clause 8-13, wherein based on every in the multiple MMSG of determination
One corresponding date appears in third time predefined section and identifies the multiple MMSG.
A kind of 15. computer program product of clause comprising:
Computer readable storage medium has the computer readable program code realized on it, and the computer can
Reader code can be implemented by processor to execute the operation for including following items:
Identify it is multiple safeguard message (MMSG), each in multiple MMSG in multiple shut-off valves in the vehicles
At least one shut-off valve is associated;
Based on the analysis of associated at least one associated multiple sensor parameters of shut-off valve with each MMSG
It identifies the first sensor parameter in the multiple sensor parameters, and the first threshold of the first sensor parameter is known
It Wei not be associated with the corresponding abnormal operation of at least one shut-off valve;
By first sensor associated with the first shut-off valve in the multiple shut-off valve, period catches at the following time
Obtain multiple values of the first sensor parameter:(i) the first time predefined section and (ii) second time predefined section, wherein institute
It states the first time predefined section and the second time predefined section is corresponding in the opening and closing of first shut-off valve
One associated;And
In the maximum value of the determining the multiple sensor values captured during the first time predefined section and in institute
It is more than first biography to state the difference between the maximum value of the multiple sensor values captured during the second time predefined section
When the first threshold of sensor parameter, determine that first shut-off valve operates singularly.
Computer program product of the clause 16. according to clause 15, the operation further include:
Generate the warning instruction for specifying the first shut-off valve operating singularly;
Warning instruction is transferred to remote computing device via network;
The warning instruction is received by the message recipient of the remote computing device;And
The maintenance of first shut-off valve is arranged by described information receiver.
Computer program product of the clause 17. according to any one of clause 15-16, wherein it is described first it is predefined when
Between section and the second time predefined section there is first time length, wherein the analysis of the multiple sensor parameters is based on institute
The value of multiple sensor parameters previously collected is stated, wherein the analysis bag includes:
Identification the multiple sensor associated with multiple opening and closing of each in the multiple shut-off valve
The value of parameter previously collected, wherein the value previously collected be identified as corresponding shut-off valve it is each opening and
Occur in the first time length after closing every time;And
For each sensor parameters in the multiple sensor parameters, each sensor for opening every time is calculated
The maximum value of phase between the maximum value of parameter and to(for) each sensor parameters of corresponding shut-off valve closed every time
Answer difference.
Computer program product of the clause 18. according to clause 17, wherein the analysis further includes:
For each sensor parameters in the multiple sensor parameters, in each of the difference based on the calculating
Standard deviation is calculated for the first percentile threshold value in multiple percentile threshold values of the difference of the calculating;And
Determine the difference each calculated associated with the first sensor parameter more than the first percentile threshold value
It is worth and occurs in the time close with the time of a MMSG in the MMSG.
Computer program product of the clause 19. according to clause 18, wherein the analysis further includes:
Determine the second percentile threshold value in the multiple percentile threshold value of the first sensor parameter with than other
Each lesser amount of false positive MMSG in multiple threshold values is associated;And
By the first threshold that the second percentile threshold definitions are the first sensor parameter.
Computer program product of the clause 20. according to clause 19, wherein the first percentile threshold value is less than described
Each in other percentile threshold values, wherein the first percentile threshold value include in the multiple sensor parameters
Three associated values of standard deviation of the difference of the calculating of each.
Although foregoing teachings are related to various aspects, it can design and be described herein without departing from its base region
Other and further aspect, and its range is indicated in the appended claims.
Claims (15)
1. a method of computer implementation comprising:
Identify it is multiple safeguard message i.e. MMSG (112), each in the multiple MMSG (112) with it is multiple in the vehicles
Shut-off valve (1021-N) at least one of shut-off valve (102N) associated;
Be based on and at least one associated multiple sensor parameters of shut-off valve associated with each MMSG (112) point
It analyses and identifies the first sensor parameter in the multiple sensor parameters, and by the first threshold of the first sensor parameter
Value is identified as and corresponding at least one shut-off valve (102N) abnormal operation it is associated;
By with the multiple shut-off valve (1021-N) in the first shut-off valve (102N) associated first sensor (103N)
Multiple values of the first sensor parameter are captured during the following time:(i) the first time predefined section and (ii) second are predetermined
The adopted period, wherein the first time predefined section and the second time predefined section and first shut-off valve (102N)
Opening and closing in corresponding one it is associated;And
Determine the maximum value of the multiple sensor values that is captured during the first time predefined section with described the
Difference between the maximum value of the multiple sensor values captured during two time predefined sections is more than the first sensor
When the first threshold of parameter, first shut-off valve (102 is determinedN) operating singularly.
2. computer implemented method according to claim 1, further includes:
It generates and specifies first shut-off valve (102N) operating singularly warning instruction;
Warning instruction is transferred to remote computing device via network;
The warning instruction is received by the message recipient (777) of the remote computing device;And
The maintenance of first shut-off valve is arranged by described information receiver (777).
3. the computer implemented method according to any one of claim 1-2, wherein first time predefined
Section and the second time predefined section have first time length, wherein the analysis of the multiple sensor parameters is based on
The value of the multiple sensor parameters previously collected, wherein the analysis bag includes:
Identification and the multiple shut-off valve (1021-N) in the associated the multiple sensing of the multiple opening and closing of each
The value of device parameter previously collected, wherein the value previously collected is identified as each opening in corresponding shut-off valve
Occur in the first time length after each close;And
For each sensor parameters in the multiple sensor parameters, each sensor parameters for opening every time are calculated
Maximum value and for the respective differences between the maximum value for each sensor parameters of corresponding shut-off valve closed every time
Value.
4. computer implemented method according to claim 3, wherein the analysis further includes:
For each sensor parameters in the multiple sensor parameters, the standard deviation of each in the difference based on calculating
Difference is calculated for the first percentile threshold value in multiple percentile threshold values of the difference of the calculating;And
Determine that the difference each calculated associated with the first sensor parameter more than the first percentile threshold value exists
The close time occurs with the time of a MMSG in the MMSG.
5. computer implemented method according to claim 4, wherein the analysis further includes:
Determine the second percentile threshold value in the multiple percentile threshold value of the first sensor parameter with it is more multiple than other
The lesser amount of false positive MMSG (112) of each of threshold value is associated;And
By the first threshold that the second percentile threshold definitions are the first sensor parameter.
6. computer implemented method according to claim 5, wherein the first percentile threshold value be less than it is described other
Each in percentile threshold value, wherein the first percentile threshold value include with for every in the multiple sensor parameters
Three associated values of standard deviation of the difference of the calculating of a sensor parameters.
7. according to the method described in any one of claim 1-6, wherein based on each of the multiple MMSG (112) is determined
The corresponding date of MMSG appears in third time predefined section and identifies the multiple MMSG (112).
8. a kind of system comprising:
One or more computer processors (704);And
Memory (706), it includes program, described program executed when being implemented by the processor include following items behaviour
Make:
Identify it is multiple safeguard message i.e. MMSG (112), each in the multiple MMSG (112) with it is multiple in the vehicles
Shut-off valve (1021-N) at least one of shut-off valve (102N) associated;
It is based on and at least one shut-off valve associated with each MMSG (112) (102N) associated multiple sensors ginseng
Several analysis and identify the first sensor parameter in the multiple sensor parameters, and by the first sensor parameter
First threshold is identified as and corresponding at least one shut-off valve (102N) abnormal operation it is associated;
By first sensor associated with the first shut-off valve in the multiple shut-off valve, period captures institute at the following time
State multiple values of first sensor parameter:(i) the first time predefined section and (ii) second time predefined section, wherein described the
One time predefined section and the second time predefined section are one corresponding in the opening and closing of first shut-off valve
It is associated;And
Determine the maximum value of the multiple sensor values that is captured during the first time predefined section with described the
Difference between the maximum value of the multiple sensor values captured during two time predefined sections is more than the first sensor
When the first threshold of parameter, determine that first shut-off valve operates singularly.
9. system according to claim 8, the operation further include:
Generate the warning instruction for specifying first shut-off valve operating singularly;
Warning instruction is transferred to remote computing device via network;
The warning instruction is received by the message recipient of the remote computing device;And
The maintenance of first shut-off valve is arranged by described information receiver.
10. according to the system described in any one of claim 8-9, wherein the first time predefined section and described second is in advance
Defining the period has first time length, wherein the analysis of the multiple sensor parameters is based on the multiple sensor
The value of parameter previously collected, wherein the analysis bag includes:
Identification and the multiple shut-off valve (1021-N) in the associated the multiple sensing of the multiple opening and closing of each
The value of device parameter previously collected, wherein the value previously collected is identified as each opening in corresponding shut-off valve
Occur in the first time length after closing;And
For each sensor parameters in the multiple sensor parameters, each sensor parameters for opening every time are calculated
Maximum value and for the respective differences between the maximum value for each sensor parameters of corresponding shut-off valve closed every time
Value.
11. system according to claim 10, wherein the analysis further includes:
For each sensor parameters in the multiple sensor parameters, the standard deviation of each in the difference based on calculating
Difference is calculated for the first percentile threshold value in multiple percentile threshold values of the difference of the calculating;And
Determine that the difference each calculated associated with the first sensor parameter more than the first percentile threshold value exists
The close time occurs with the time of a MMSG in the MMSG (112).
12. according to the system described in any one of claim 8-11, wherein the analysis further includes:
Determine the second percentile threshold value in the multiple percentile threshold value of the first sensor parameter with it is more multiple than other
The lesser amount of false positive MMSG (112) of each threshold value in threshold value is associated;And
By the first threshold that the second percentile threshold definitions are the first sensor parameter.
13. system according to claim 12, wherein the first percentile threshold value is less than other described percentile threshold values
In each, wherein the first percentile threshold value include with for each in the multiple sensor parameters the meter
Three associated values of standard deviation of the difference of calculation.
14. according to the system described in any one of claim 8-13, wherein every in the multiple MMSG (112) based on determining
The corresponding date of one MMSG appears in third time predefined section and identifies the multiple MMSG (112).
15. a kind of computer program product comprising:
Computer readable storage medium (706) has the computer readable program code realized on it, and the computer can
Reader code can be implemented by processor (704) to execute the operation including following items:
Identify it is multiple safeguard message i.e. MMSG (112), each in the multiple MMSG (112) with multiple sections in the vehicles
Only valve (1021-N) at least one of shut-off valve (102N) associated;
It is based on and at least one shut-off valve associated with each MMSG (112) (102N) associated multiple sensors ginseng
Several analysis and identify the first sensor parameter in the multiple sensor parameters, and by the first sensor parameter
First threshold is identified as and corresponding at least one shut-off valve (102N) abnormal operation it is associated;
By with the multiple shut-off valve (1021-N) in the associated first sensor of the first shut-off valve at the following time during
Capture multiple values of the first sensor parameter:(i) the first time predefined section and (ii) second time predefined section, wherein
The first time predefined section and the second time predefined section and the phase in the opening and closing of first shut-off valve
Answering one is associated;And
Determine the maximum value of the multiple sensor values that is captured during the first time predefined section with described the
Difference between the maximum value of the multiple sensor values captured during two time predefined sections is more than the first sensor
When the first threshold of parameter, determine that first shut-off valve operates singularly.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US15/464,044 US11080660B2 (en) | 2017-03-20 | 2017-03-20 | Data-driven unsupervised algorithm for analyzing sensor data to detect abnormal valve operation |
US15/464,044 | 2017-03-20 |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108628282A true CN108628282A (en) | 2018-10-09 |
CN108628282B CN108628282B (en) | 2022-11-04 |
Family
ID=61274042
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810207808.5A Active CN108628282B (en) | 2017-03-20 | 2018-03-14 | Data driven unsupervised algorithm to analyze sensor data to detect abnormal valve operation |
Country Status (5)
Country | Link |
---|---|
US (1) | US11080660B2 (en) |
EP (1) | EP3379359B1 (en) |
JP (1) | JP7186007B2 (en) |
CN (1) | CN108628282B (en) |
SG (1) | SG10201800997UA (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111522247A (en) * | 2020-05-09 | 2020-08-11 | 刘玉华 | Method for detecting abnormity of multiple sensors in intelligent home system |
CN111522246A (en) * | 2020-05-09 | 2020-08-11 | 刘玉华 | Method for detecting abnormity of single sensor in intelligent home system |
CN111860645A (en) * | 2020-07-20 | 2020-10-30 | 中科三清科技有限公司 | Method and device for repairing default value in volatile organic compound observation data |
Families Citing this family (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP6741716B2 (en) | 2018-04-09 | 2020-08-19 | 株式会社Subaru | Aircraft management system |
US11238417B2 (en) | 2020-02-28 | 2022-02-01 | The Boeing Company | Adjusting maintenance intervals for individual platforms based on observable conditions |
US11465778B2 (en) * | 2020-03-04 | 2022-10-11 | The Boeing Company | Pump management system |
WO2022014714A1 (en) * | 2020-07-17 | 2022-01-20 | 日精エー・エス・ビー機械株式会社 | Operation abnormality detection method, method for manufacturing resin container, operation abnormality detection device, device for manufacturing resin container, and device for manufacturing resin preform |
JP2022133074A (en) * | 2021-03-01 | 2022-09-13 | 三菱重工業株式会社 | Valve operation abnormality detection system, valve operation abnormality detection method and program |
GB2607114A (en) * | 2021-05-27 | 2022-11-30 | Airbus Operations Ltd | A method of determining an operating condition of a valve of an aircraft system |
US20230413744A1 (en) * | 2022-06-27 | 2023-12-28 | Uniflood LLC | Sustainable residential yard flood irrigation valve system with controller |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20030197739A1 (en) * | 2002-04-23 | 2003-10-23 | Bauer Jason M. | Distribution of application windows in a computing device display |
CN101194388A (en) * | 2005-06-06 | 2008-06-04 | 丰田自动车株式会社 | Error judgment device |
CN101359228A (en) * | 2008-09-09 | 2009-02-04 | 张东来 | Electromagnetic control element failure diagnosis method and device based on variation of electric current at drive end |
CN101799365A (en) * | 2008-12-23 | 2010-08-11 | 巴西航空有限公司 | The performance monitoring of aircraft pneumatic control valves and forecast |
JP2013200719A (en) * | 2012-03-26 | 2013-10-03 | Aisin Aw Co Ltd | Controller of solenoid valve and abnormality determination method for the same |
JP2014211160A (en) * | 2013-04-16 | 2014-11-13 | ジーイー・アビエイション・システムズ・リミテッドGe Aviation Systems Limited | Method for predicting bleed air system fault |
CN104541216A (en) * | 2012-08-21 | 2015-04-22 | 通用电气公司 | Monitoring system and method for detecting the change of a mechanical system |and adapting the limit values associated to said mechanical system to reflect|the current conditions of the mechanical system |
US20160186890A1 (en) * | 2013-08-09 | 2016-06-30 | Snecma | Method for monitoring a valve of an aircraft engine |
Family Cites Families (47)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP3530775B2 (en) * | 1999-07-16 | 2004-05-24 | Smc株式会社 | Solenoid valve operation management device |
US20050267709A1 (en) * | 2004-05-28 | 2005-12-01 | Fisher-Rosemount Systems, Inc. | System and method for detecting an abnormal situation associated with a heater |
US7536274B2 (en) * | 2004-05-28 | 2009-05-19 | Fisher-Rosemount Systems, Inc. | System and method for detecting an abnormal situation associated with a heater |
US20060174707A1 (en) * | 2005-02-09 | 2006-08-10 | Zhang Jack K | Intelligent valve control methods and systems |
US8250017B2 (en) * | 2007-08-23 | 2012-08-21 | General Electric Company | System and method for prediction of gas turbine trips due to gas control valve failures |
US8463641B2 (en) * | 2007-10-05 | 2013-06-11 | The Boeing Company | Method and system using linear programming for estimating test costs for bayesian diagnostic models |
US7996096B2 (en) * | 2008-02-29 | 2011-08-09 | Fisher Controls International Llc | Estimation of process control parameters over predefined travel segments |
US20100023201A1 (en) * | 2008-07-24 | 2010-01-28 | David Scott Kinney | Method and apparatus for obtaining vehicle data |
US8749239B2 (en) * | 2008-10-02 | 2014-06-10 | Certusview Technologies, Llc | Locate apparatus having enhanced features for underground facility locate operations, and associated methods and systems |
US8442766B2 (en) * | 2008-10-02 | 2013-05-14 | Certusview Technologies, Llc | Marking apparatus having enhanced features for underground facility marking operations, and associated methods and systems |
US8118256B2 (en) | 2008-10-10 | 2012-02-21 | Goodrich Corporation | Brake shutoff valve test |
FI125797B (en) * | 2009-01-09 | 2016-02-29 | Metso Flow Control Oy | Method and equipment for valve condition monitoring |
US8378853B2 (en) * | 2009-11-18 | 2013-02-19 | Honeywell International Inc. | Intelligent crew alerting system and method for aircraft and other vehicle applications |
US20110125348A1 (en) * | 2009-11-23 | 2011-05-26 | Gordon Robert Andrew Sandell | Automatic Emergency Reporting |
US8996328B2 (en) | 2009-12-29 | 2015-03-31 | Fisher Controls International Llc | Methods, apparatus and articles of manufacture to test safety instrumented system solenoids |
US8434301B2 (en) * | 2010-04-16 | 2013-05-07 | Nabtesco Corporation | Local backup hydraulic actuator for aircraft control systems |
JP5588260B2 (en) * | 2010-08-02 | 2014-09-10 | ナブテスコ株式会社 | Aircraft actuator control system |
US10558544B2 (en) * | 2011-02-14 | 2020-02-11 | International Business Machines Corporation | Multiple modeling paradigm for predictive analytics |
US8838413B2 (en) * | 2011-05-12 | 2014-09-16 | Saudi Arabian Oil Company | Valve actuator fault analysis system |
US8768534B2 (en) * | 2011-11-14 | 2014-07-01 | Arinc Incorporated | Method and apparatus for using electronic flight bag (EFB) to enable flight operations quality assurance (FOQA) |
US20130197739A1 (en) * | 2012-01-31 | 2013-08-01 | Gulfstream Aerospace Corporation | Methods and systems for aircraft health and trend monitoring |
FR2987398B1 (en) * | 2012-02-24 | 2017-07-21 | Snecma | SYSTEM FOR DETECTING FAILURE PREMISES OF A VALVE OF AN AIRCRAFT ENGINE |
US9726643B2 (en) * | 2012-12-28 | 2017-08-08 | Vetco Gray Inc. | Gate valve real time health monitoring system, apparatus, program code and related methods |
US9885317B2 (en) * | 2013-05-10 | 2018-02-06 | ProAct Services Corporation | System and method for combusting volatile vapors |
US9695956B2 (en) * | 2013-07-29 | 2017-07-04 | Dresser, Inc. | Spectral analysis based detector for a control valve |
JP6216633B2 (en) * | 2013-12-13 | 2017-10-18 | アズビル株式会社 | Valve abnormality detection device and method |
WO2015124890A1 (en) * | 2014-02-21 | 2015-08-27 | Taleris Global Llp | Method for diagnosing a fault in an air-conditioning pack of an aircraft |
CN111504364B (en) * | 2014-02-21 | 2023-03-17 | 特莱丽思环球有限合伙公司 | Method for predicting a fault in an air-conditioning pack of an aircraft |
CN106164794A (en) * | 2014-02-21 | 2016-11-23 | 特莱丽思环球有限合伙公司 | The method of the fault in the cabin temperature control system predicting aircraft |
US9567106B2 (en) * | 2014-11-21 | 2017-02-14 | Taleris Global Llp | System and method for identifying faults in an aircraft |
US9546604B2 (en) | 2015-01-08 | 2017-01-17 | United Technologies Corporation | Transient fault detection methods and systems |
US9558601B2 (en) * | 2015-04-24 | 2017-01-31 | The Boeing Company | System and method for detecting vehicle system faults |
US9739682B2 (en) * | 2015-05-04 | 2017-08-22 | Dresser, Inc. | Valve assembly calibration |
CN107735744B (en) * | 2015-09-04 | 2020-06-30 | 慧与发展有限责任合伙企业 | Systems, methods, and media for valve failure prediction |
EP3354885A4 (en) * | 2015-09-25 | 2019-01-02 | Nissan Motor Co., Ltd. | Valve control device |
US10527191B2 (en) * | 2015-12-15 | 2020-01-07 | Sdb Ip Holdings, Llc | System, method, and apparatus for monitoring restroom appliances |
US9971328B2 (en) * | 2016-01-27 | 2018-05-15 | Michael Anthony Kaminski | Flow control center sensing pressure by barometric sensor and emit sensed pressure signal |
US20170243413A1 (en) * | 2016-02-22 | 2017-08-24 | Hamilton Sundstrand Corporation | Method for determining aircraft sensor failure without a redundant sensor and correct sensor measurement when redundant aircraft sensors give inconsistent readings |
US9724979B1 (en) * | 2016-04-27 | 2017-08-08 | The Boeing Company | Model-based method to detect abnormal operations in heat exchangers |
US10444121B2 (en) * | 2016-05-03 | 2019-10-15 | Sap Se | Fault detection using event-based predictive models |
GB201607791D0 (en) * | 2016-05-04 | 2016-06-15 | Rolls Royce | Method to determine a state of a valve and valve monitoring apparatus |
US10558929B2 (en) * | 2016-05-31 | 2020-02-11 | The Boeing Company | Monitored machine performance as a maintenance predictor |
FR3055358B1 (en) * | 2016-08-25 | 2018-08-17 | Safran Aircraft Engines | METHOD FOR MANAGING A TURBOMACHINE STARTER VALVE FAILURE |
US20180172556A1 (en) * | 2016-12-15 | 2018-06-21 | General Electric Company | Systems and Methods to Predict Valve Performance in Power Plants |
US9915375B1 (en) * | 2017-02-10 | 2018-03-13 | Fisher Controls International Llc | Methods and apparatus to monitor health information of a valve |
US10703464B2 (en) * | 2018-07-12 | 2020-07-07 | Goodrich Corporation | Architecture for locked wheel and antiskid performance |
JP6564544B1 (en) * | 2019-04-19 | 2019-08-21 | 株式会社ブイテックス | Control method of gate valve |
-
2017
- 2017-03-20 US US15/464,044 patent/US11080660B2/en active Active
-
2018
- 2018-02-02 EP EP18155004.7A patent/EP3379359B1/en active Active
- 2018-02-05 SG SG10201800997UA patent/SG10201800997UA/en unknown
- 2018-03-14 CN CN201810207808.5A patent/CN108628282B/en active Active
- 2018-03-20 JP JP2018052061A patent/JP7186007B2/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20030197739A1 (en) * | 2002-04-23 | 2003-10-23 | Bauer Jason M. | Distribution of application windows in a computing device display |
CN101194388A (en) * | 2005-06-06 | 2008-06-04 | 丰田自动车株式会社 | Error judgment device |
CN101359228A (en) * | 2008-09-09 | 2009-02-04 | 张东来 | Electromagnetic control element failure diagnosis method and device based on variation of electric current at drive end |
CN101799365A (en) * | 2008-12-23 | 2010-08-11 | 巴西航空有限公司 | The performance monitoring of aircraft pneumatic control valves and forecast |
JP2013200719A (en) * | 2012-03-26 | 2013-10-03 | Aisin Aw Co Ltd | Controller of solenoid valve and abnormality determination method for the same |
CN104541216A (en) * | 2012-08-21 | 2015-04-22 | 通用电气公司 | Monitoring system and method for detecting the change of a mechanical system |and adapting the limit values associated to said mechanical system to reflect|the current conditions of the mechanical system |
JP2014211160A (en) * | 2013-04-16 | 2014-11-13 | ジーイー・アビエイション・システムズ・リミテッドGe Aviation Systems Limited | Method for predicting bleed air system fault |
US20160186890A1 (en) * | 2013-08-09 | 2016-06-30 | Snecma | Method for monitoring a valve of an aircraft engine |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111522247A (en) * | 2020-05-09 | 2020-08-11 | 刘玉华 | Method for detecting abnormity of multiple sensors in intelligent home system |
CN111522246A (en) * | 2020-05-09 | 2020-08-11 | 刘玉华 | Method for detecting abnormity of single sensor in intelligent home system |
CN111522246B (en) * | 2020-05-09 | 2023-06-23 | 武汉汉昇电子科技有限公司 | Abnormality detection method for single sensor in intelligent home system |
CN111522247B (en) * | 2020-05-09 | 2023-07-14 | 上海正项信息科技有限公司 | Abnormality detection method for multiple sensors in intelligent home system |
CN111860645A (en) * | 2020-07-20 | 2020-10-30 | 中科三清科技有限公司 | Method and device for repairing default value in volatile organic compound observation data |
CN111860645B (en) * | 2020-07-20 | 2021-04-13 | 中科三清科技有限公司 | Method and device for repairing default value in volatile organic compound observation data |
Also Published As
Publication number | Publication date |
---|---|
US20180266584A1 (en) | 2018-09-20 |
EP3379359B1 (en) | 2022-04-06 |
EP3379359A1 (en) | 2018-09-26 |
SG10201800997UA (en) | 2018-10-30 |
JP2018185799A (en) | 2018-11-22 |
US11080660B2 (en) | 2021-08-03 |
JP7186007B2 (en) | 2022-12-08 |
CN108628282B (en) | 2022-11-04 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108628282A (en) | Analyte sensors data are to detect the unsupervised algorithm of data-driven of abnormal valve operation | |
EP3441947B1 (en) | System and method for remaining useful life determination | |
EP3096123B1 (en) | System and methods for management and monitoring of aerial vehicles | |
CN103809585B (en) | Method and apparatus for the field device in access control system | |
US8914149B2 (en) | Platform health monitoring system | |
US8599044B2 (en) | System and method to assess and report a health of a tire | |
US20160239756A1 (en) | Correlation and annotation of time series data sequences to extracted or existing discrete data | |
US20200143292A1 (en) | Signature enhancement for deviation measurement-based classification of a detected anomaly in an industrial asset | |
EP3055746B1 (en) | Correlation and annotation of time series data sequences to extracted or existing discrete data | |
US11549611B2 (en) | Fault prediction in valve systems through Bayesian framework | |
KR102118748B1 (en) | Platform health monitoring system | |
CN110109428A (en) | A kind of dangerous situation monitoring system for laboratory equipment | |
Iftikhar et al. | Real-time Visualization of Sensor Data in Smart Manufacturing using Lambda Architecture. | |
US11262743B2 (en) | Predicting leading indicators of an event | |
US11807388B2 (en) | Apparatus, method and computer program for monitoring an aircraft engine | |
US20160195872A1 (en) | System for Assisting Operation at the Time of Plant Accident and Method for Assisting Operation at the Time of Plant Accident | |
Ploennigs et al. | Extending semantic sensor networks for automatically tackling smart building problems | |
Liang et al. | Production Command Cockpit Safety Management System Based on Deep Neural Network | |
Chepizhenko et al. | Maintenance Intervals Appointment on the Basis of Model of Aircraft Systems Function State Changing | |
CN115281734A (en) | Nucleic acid sampling auxiliary system | |
KR101627436B1 (en) | System and method for ils management | |
CN117831026A (en) | Food quality detection method and device based on machine learning |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |